INDEX

Explanations

references to posthumous activities or items

oai_token-act-pair · gpt-3.5-turbo

terms related to posthumous works and references to offices

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ONSORED

-0.77

irlf

-0.71

GREEN

-0.63

EFF

-0.62

amiya

-0.62

OST

-0.61

EMP

-0.59

ENG

-0.58

 Mahjong

-0.58

 principals

-0.57

POSITIVE LOGITS

antage

0.88

umatic

0.87

opausal

0.87

ocalyptic

0.78

urse

0.76

lict

0.76

ritic

0.76

herry

0.74

zon

0.72

ortal

0.72

Activations Density 0.100%

references to posthumous activities or items

terms related to posthumous works and references to offices

No Comments

No Known Activations